AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
Google Cloud Security Blog · November 10, 2026

CodeMender pull requests: preserve evidence and fail safely

news AI Red TeamingAI EngineeringAgent Security
Why it matters

Google describes a pull-request workflow that proposes security patches and retains sandbox verification traces. Its reference architecture highlights a critical failure mode: a crashed or timed-out exploit test must remain inconclusive. The article also explains repository-scoped OIDC trust and the branch protection needed to enforce its status check. This is an implementation guide, not an independent effectiveness evaluation.

My takeaway: Require branch protection for the security check, scope OIDC trust to immutable repository identifiers, and isolate verification jobs from secrets and outbound access. Test crash and timeout handling explicitly, preserve traces, and review and retest generated patches before merging.
Keep exploring

More curated notes connected through AI Red Teaming and AI Engineering.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.